AswanthCManoj commited on
Commit
a55c993
·
verified ·
1 Parent(s): 3a61cb7

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1,4 +1,8 @@
1
  {
 
 
2
  "<|im_end|>": 32000,
3
- "<|im_start|>": 32001
 
 
4
  }
 
1
  {
2
+ "<|end|>": 32002,
3
+ "<|function_call|>": 32005,
4
  "<|im_end|>": 32000,
5
+ "<|im_start|>": 32001,
6
+ "<|response|>": 32004,
7
+ "<|thoughts|>": 32003
8
  }
special_tokens_map.json CHANGED
@@ -1,6 +1,18 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "</s>",
5
  "unk_token": "<unk>"
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
  "pad_token": "</s>",
17
  "unk_token": "<unk>"
18
  }
tokenizer_config.json CHANGED
@@ -41,13 +41,45 @@
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  }
45
  },
46
  "additional_special_tokens": [],
47
  "bos_token": "<s>",
48
- "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
49
  "clean_up_tokenization_spaces": false,
50
- "eos_token": "</s>",
51
  "legacy": true,
52
  "model_max_length": 1000000000000000019884624838656,
53
  "pad_token": "</s>",
 
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|end|>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32003": {
54
+ "content": "<|thoughts|>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32004": {
62
+ "content": "<|response|>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "32005": {
70
+ "content": "<|function_call|>",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
  }
77
  },
78
  "additional_special_tokens": [],
79
  "bos_token": "<s>",
80
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
81
  "clean_up_tokenization_spaces": false,
82
+ "eos_token": "<|im_end|>",
83
  "legacy": true,
84
  "model_max_length": 1000000000000000019884624838656,
85
  "pad_token": "</s>",